An Autonomous Incremental Learning Algorithm for Radial Basis Function Networks

Ozawa, Seiichi; Tabuchi, Toshihisa; Nakasaka, Sho; Roy, Asim

doi:10.4236/jilsa.2010.24021

Cited by 5 publications

(3 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In conventional RAN, the problem is solved by learning local region which is approximated using C 1 continuous polynomial without calculating the RBF outputs (Platt 1991). Whereas, the same goal is achieved by another variant of RAN, RAN with Long Term Memory (RAN-LTM) where it carried out the learning with memory items that are stored in LTM (Kobayashi et al 2001, Okamoto et al 2003, Ozawa et al 2010). Nevertheless, we use different approach which can be easily implemented by using LSH where we are able to select active RBF units.…”

Section: : Loopmentioning

confidence: 99%

A fast online learning algorithm of radial basis function network with locality sensitive hashing

2016

Self Cite

View full text Add to dashboard Cite

In this paper, we propose a new incremental learning algorithm of Radial Basis Function (RBF) Network to accelerate the learning for largescale data sequence. Along with the development of the internet and sensor technologies, a time series of large data chunk are continuously generated in our daily life. Thus it is usually difficult to learn all the data within a short period. A remedy for this is to select only essential data from a given data chunk and provide them to a classifier model to learn. In the proposed method, only data in untrained regions, which correspond to a region with a low output margin, are selected. The regions are formed by grouping the data based on their near neighbor using Locality Sensitive Hashing (LSH), in which LSH has been developed to search neighbors quickly in an approximated way. As the proposed method does not use all training data to calculate the output margins, the time of the data selection is expected to be shortened. In the incremental learning phase, in order to suppress catastrophic forgetting, we also exploit LSH to select neighbor RBF units quickly. In addition, we propose a method to update the hash table in LSH so that the data selection can be adaptive during the learning. From the performance of nine datasets, we confirm that the proposed method can learn large-scale data sequences fast without sacrificing the classification accuracies. This fact implies that the data selection and the incremental learning work effectively in the proposed method.

show abstract

Section: : Loopmentioning

confidence: 99%

A fast online learning algorithm of radial basis function network with locality sensitive hashing

2016

Self Cite

View full text Add to dashboard Cite

show abstract

“…It needs to keep intact the formed clusters while incrementally accommodating the new data. Formation of the clusters with respect to the underlying pattern [11] of the data is now considered during the process of learning incrementally [12].…”

Section: Related Workmentioning

confidence: 99%

Decision-Making in Multi-Perspective Environment withIncremental Learning

Joshi¹,

Kulkarni²

2012

IJMO

View full text Add to dashboard Cite

In many applications that require decision making, dependency is on the data obtained from various sources. Each source of information provides a different perspective to the problem domain. With the existing data that is available and new perspective that evolves at later stages, there is need to learn incrementally. In this paper we recognize the similarity between the new perspective and the existing knowledge based on their pattern. The proposed work, referred as 'Multi-Perspective based Incremental Learning' [MPIL], effectively modifies the knowledge with available perspectives, understands the patterns of the data to determine the update and at the same time maintains them for reuse. With application to education sector, experiments show that the proposed approach exhibit better decision-making capacity in a multi-perspective environment.

show abstract

“…Figure 3 illustrates how labeled spam emails are trained in (a) batch learning scheme and (b) incremental learning scheme. In the batch learning scheme, we adopt the conventional RBF network (RBFN) (i.e., RBFN usually used as batch learning [25]) as a classifier and a sliding window is introduced to define a data set to be trained every day. In this experiment, the time-window size is preliminarily determined as 12 days via the crossvalidation using the spam emails collected during a different period.…”

Section: Methodsmentioning

confidence: 99%